arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Massachusetts Institute of Technology(麻省理工学院)

2026-07-15 至 2026-07-15 共收录 7
2607.12370 2026-07-15 cs.RO 新提交

StratMamba: Strategic and Reactive Stream Partitioning for Path-Efficient LiDAR-Based Obstacle Avoidance

StratMamba:用于基于路径高效的激光雷达避障的策略性和反应性流划分

Hung-Chieh Wu, Xiaopan Zhang, Kasra Sinaei, Ryan Abnavi, Kasun Weerakoon, Christopher Bradley, Seyed Fakoorian, Jiachen Li, Donald Ebeigbe

机构 * The Pennsylvania State University(宾夕法尼亚州立大学) AlphaZ, Inc.(阿尔法兹公司) Georgia Institute of Technology(佐治亚理工学院) Massachusetts Institute of Technology(麻省理工学院)

AI总结 研究针对复杂环境中机器人导航问题,提出StratMamba双流时间建模架构,结合快慢衰减内存架构处理激光雷达数据。经多场景评估及与其他基线对比,其在时间推理效率、导航速度和路径最优性方面表现出色,在现实中性能更稳健。

Comments Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026). 8 pages, 6 figures. Video: https://www.youtube.com/watch?v=Z0FfO_AVaSw

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.11946 2026-07-15 cs.CL eess.AS 新提交

Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification

用于低资源澳大利亚原住民语言识别的混合持续学习

Pravina Mylvaganam, Ting Dang, Eliathamby Ambikairajah, Vidhyasaharan Sethu, Jingyao Wu

机构 * University of New South Wales(新南威尔士大学) University of Melbourne(墨尔本大学) Massachusetts Institute of Technology(麻省理工学院)

AI总结 针对低资源澳大利亚原住民语言识别中数据稀缺和灾难性遗忘问题,提出重放增强弹性权重巩固和约束引导知识蒸馏两种混合持续学习方法,实验表明其优于微调及现有基线,能提升对多种AAL的适应性并保持对高资源语言的性能。

Comments Accepted by Interspeech 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.12902 2026-07-15 stat.ML cs.DS cs.LG math.PR math.ST stat.CO stat.TH 新提交

Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo

随机哈密顿蒙特卡罗算法的加速混合时间

Siddharth Mitra, Vishwak Srinivasan, Xiuyuan Wang, Andre Wibisono

机构 * Department of Computer Science, Yale University(耶鲁大学计算机科学系) Department of Electrical Engineering and Computer Science, MIT(麻省理工学院电气工程与计算机科学系)

AI总结 研究随机哈密顿蒙特卡罗算法在从对数凹概率分布采样时的加速混合时间,通过使用特定随机积分时间,证明其在KL散度中指数收敛,给出不同情况下达到误差ε的总积分时间的尺度,分析依赖于平均KL散度的界。

Comments 74 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05686 2026-07-15 cs.AI 版本更新

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

Transformer记忆的吸引子几何:从冲突仲裁到自信 hallucination

Qiyao Liang, Risto Miikkulainen, Ila Fiete

机构 * Massachusetts Institute of Technology(麻省理工学院) University of Texas Austin(德克萨斯大学奥斯汀分校) Cognizant(Cognizant公司)

AI总结 研究Transformer记忆中冲突与hallucination的几何机制,揭示吸引子基底在隐藏状态空间中的作用,通过合成任务验证几何边界在区分正确回忆与hallucination中的有效性。

Comments Inadvertent premature posting before full approval of all listed co-authors

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16918 2026-07-15 cs.CV cs.AI 版本更新

Xray-Visual Models: Scaling Vision models on Industry Scale Data

Xray-Visual模型:在产业级数据上扩展视觉模型

Shlok Mishra, Tsung-Yu Lin, Linda Wang, Hongli Xu, Yimin Liu, Michael Hsu, Chaitanya Ahuja, Hao Yuan, Jianpeng Cheng, Hong-You Chen, Haoyuan Xu, Chao Li, Sreya Dutta Roy, Abhijeet Awasthi, Jihye Moon, Don Husa, Michael Ge, Sumedha Singla, Arkabandhu Chowdhury, Phong Dingh, Satya Narayan Shukla, Yonghuan Yang, David Jacobs, Qi Guo, Jun Xiao, Xiangjun Fan, Aashu Singh

机构 * Meta-AI MIT(麻省理工学院) University of Maryland(马里兰大学)

AI总结 Xray-Visual通过三阶段训练流程和LLM2CLIP技术,在产业级数据上实现高效多模态视觉模型,取得最佳性能并提升鲁棒性与泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24372 2026-07-15 cs.LG cs.AI cs.NE 版本更新

Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning

大规模进化策略:超越强化学习的LLM微调

Xin Qiu, Yulu Gan, Conor F. Hayes, Qiyao Liang, Yinggan Xu, Roberto Dailey, Elliot Meyerson, Babak Hodjat, Risto Miikkulainen

机构 * University of California, Los Angeles, Los Angeles, CA, USA(加州大学洛杉矶分校) Cognizant AI Lab, San Francisco, CA, USA(Cognizant AI实验室) The University of Texas at Austin, Austin, TX, USA(德克萨斯大学奥斯汀分校) Massachusetts Institute of Technology, Cambridge, MA, USA(麻省理工学院)

AI总结 本文提出使用进化策略进行大规模LLM微调,证明其在多个方面优于强化学习,为LLM微调提供了新的方法。

Comments Published at ICML 2026 main conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01241 2026-07-15 cs.CY cs.AI 版本更新

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

首先,不伤害:迈向临床安全的大语言模型

David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj, Priyank Jain, Jessica Tran, Matthew Gwiazdon, Arjun Rustagi, Jenelle Jindal, Jacob M. Koshy, Vinay Kadiyala, Anup Agarwal, Bassman Tappuni, Brianna French, Sirus Jesudasen, Christopher V. Cosgriff, Rebanta Chakraborty, Jillian Caldwell, Susan Ziolkowski, David J. Iberri, Robert Diep, Rahul S. Dalal, Kira L. Newman, Kristin Galetta, J. Carl Pallais, Nancy Wei, Kathleen M. Buchheit, David I. Hong, Vartan Pahalyants, Ernest Y. Lee, Allen Shih, Tamara B. Kaplan, Vishnu Ravi, Sarita Khemani, Thomas A. Buckley, April S. Liang, Daniel Shirvani, Advait Patil, Nicholas Marshall, Kanav Chopra, Joel Koh, Adi Badhwar, Anastasia Perez, Austin J. Schoeffler, Mahbuba Tusty, Chase M. Walton, Liam G. McCoy, David J. H. Wu, Yingjie Weng, Sumant Ranji, Kevin Schulman, Nigam H. Shah, Jason Hom, Arnold Milstein, Arjun K. Manrai, Adam Rodman, Jonathan H. Chen, Ethan Goh

机构 * Harvard Combined Dermatology Program(哈佛联合皮肤科项目) Department of Dermatology, Mass General Brigham(麻省总医院皮肤科) Harvard Medical School(哈佛医学院) Stanford Center for Biomedical Informatics Research(斯坦福生物医学信息学研究中心) Stanford University(斯坦福大学) Division of Hospital Medicine, Department of Medicine, Stanford University School of Medicine(斯坦福大学医学院医院医学科) Department of Medicine, Cambridge Health Alliance(剑桥健康联盟医学科) Beth Israel Deaconess Hospital–Plymouth(贝塞斯达德acons医院-普利茅斯) Department of Medicine, University of California, San Francisco(加州大学旧金山分校医学科) Department of Neurology, Stanford University School of Medicine(斯坦福大学医学院神经科) Department of Medicine, Beth Israel Deaconess Medical Center(贝塞斯达德acons医学中心医学科) Division of Cardiology, Department of Medicine, Cambridge Health Alliance(剑桥健康联盟心脏病科) Department of Cardiovascular Medicine, Summa Health System(Summa健康系统心血管医学科) Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, University of Wisconsin-Madison(威斯康星大学麦迪逊分校医学科过敏、呼吸科和危重医学科) Division of Pulmonary and Critical Care Medicine, Department of Medicine, Massachusetts General Hospital(麻省总医院呼吸科和危重医学科) Center for Immunology and Inflammatory Diseases, Department of Medicine, Massachusetts General Hospital(麻省总医院免疫和炎症疾病中心) Broad Institute of MIT and Harvard(MIT和哈佛Broad研究所) Division of Pulmonary, Critical Care, and Sleep Medicine, Cambridge Health Alliance(剑桥健康联盟呼吸科、危重医学科和睡眠医学科)

AI总结 提出NOHARM基准,包含1100个初级到专科咨询案例,评估28个LLM的医疗建议安全性,发现高达22.6%的案例存在严重危害风险,其中遗漏错误占80%以上。

详情

展开后加载摘要…

URL PDF HTML 收藏